caveman-compress

Compress verbose Claude Code memory files into token-efficient prose in place.

Updated Aug 23, 2026

Search Tags:#context #optimization #claude #memory #token #compress #caveman

Ready to run

npx skills add https://github.com/izo/Ulk --skill caveman-compress-izo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman-compress
Source: https://github.com/izo/Ulk/tree/main/community-skills/caveman/caveman-compress
Command: npx skills add https://github.com/izo/Ulk --skill caveman-compress-izo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory bloat in CLAUDE.md and other context files slows processing and wastes tokens. Caveman Compress rewrites verbose prose into dense, information-preserving shorthand while preserving semantics.

Core Features & Use Cases

Rewrites CLAUDE.md, specs, and notes into compact form without losing meaning
Preserves all semantic content including code blocks, lists, and instructions, while removing filler preambles
Use Case: before a long session or memory distribution to minimize token usage during context audits

Quick Start

Run /caveman-compress CLAUDE.md to compress its content in place and report the token savings.

Frequently Asked Questions about caveman-compress

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I compress CLAUDE.md memory files to save tokens?▼

To compress CLAUDE.md memory files and save tokens, you can rewrite verbose prose into dense, information-preserving shorthand that preserves all semantic content while removing filler preambles.

What is context compression for Claude Code memory?▼

Context compression for Claude Code memory is the process of rewriting verbose context files into terse, token-efficient prose to prevent memory bloat from slowing processing and wasting tokens.

Does compressing context files preserve code blocks and YAML frontmatter?▼

Yes, compressing context files preserves code blocks and YAML frontmatter. The compression rewrites prose in-place while excluding code blocks and YAML frontmatter as required.

When should I compress my context files before a long session?▼

You should compress context files before a long session, before memory distribution, or during long-context audits when files exceed token limits to minimize token usage.

What is the best way to reduce token usage in Claude Code memory?▼

The best way to reduce token usage in Claude Code memory is to rewrite verbose specs and notes into compact form without losing meaning, reporting the exact token savings after compression.

Are there limitations to compressing memory files in place?▼

A limitation of compressing memory files in place is that while it preserves all semantic content, it transforms the original prose into dense shorthand, altering the original file format permanently.